On the Revision of Probabilistic Beliefs Using Uncertain Evidence
Abstract
We revisit the problem of revising probabilistic beliefs using uncertain evidence, and report results on several major issues relating to this problem: how should one specify uncertain evidence? How should one revise a probability distribution? How should one interpret informal evidential statements? Should, and do, iterated belief revisions commute? And what guarantees can be offered on the amount of belief change induced by a particular revision? Our discussion is focused on two main methods for probabilistic revision: Jeffrey's rule of probability kinematics and Pearl's method of virtual evidence, where we analyze and unify these methods from the perspective of the questions posed above.
Cite
Text
Chan and Darwiche. "On the Revision of Probabilistic Beliefs Using Uncertain Evidence." International Joint Conference on Artificial Intelligence, 2003. doi:10.1016/j.artint.2004.09.005Markdown
[Chan and Darwiche. "On the Revision of Probabilistic Beliefs Using Uncertain Evidence." International Joint Conference on Artificial Intelligence, 2003.](https://mlanthology.org/ijcai/2003/chan2003ijcai-revision/) doi:10.1016/j.artint.2004.09.005BibTeX
@inproceedings{chan2003ijcai-revision,
title = {{On the Revision of Probabilistic Beliefs Using Uncertain Evidence}},
author = {Chan, Hei and Darwiche, Adnan},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2003},
pages = {99-105},
doi = {10.1016/j.artint.2004.09.005},
url = {https://mlanthology.org/ijcai/2003/chan2003ijcai-revision/}
}